Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15754
    Prev
    Next
    INDEX
    Explanations

    references to social interactions and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    This neuron detects sentence beginnings, particularly detecting "It is" or "This is" at the start of sentences and paragraphs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @iarcuschin
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.42
     privées
    -0.38
     arşivlendi
    -0.38
     privados
    -0.38
    Irlande
    -0.37
     choque
    -0.36
     cedo
    -0.36
    ыгана
    -0.36
    latego
    -0.35
     senador
    -0.35
    POSITIVE LOGITS
     ujednoznacz
    0.52
    ">//
    0.50
    ValueStyle
    0.48
     Exacts
    0.46
     EconPapers
    0.44
    icator
    0.44
    ględ
    0.44
    下载附件
    0.43
    addPreferredGap
    0.43
    ViewStyle
    0.43
    Activations Density 0.813%

    No Known Activations